English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Brain networks have received considerable attention given the criticalsignificance for understanding human brain organization, for investigatingneurological disorders and for clinical diagnostic applications. Structuralbrain network (e.g. DTI) and functional brain network (e.g. fMRI) are theprimary networks of interest. Most existing works in brain network analysisfocus on either structural or functional connectivity, which cannot leveragethe complementary information from each other. Although multi-view learningmethods have been proposed to learn from both networks (or views), thesemethods aim to reach a consensus among multiple views, and thus distinctintrinsic properties of each view may be ignored. How to jointly learnrepresentations from structural and functional brain networks while preservingtheir inherent properties is a critical problem. In this paper, we propose aframework of Siamese community-preserving graph convolutional network (SCP-GCN)to learn the structural and functional joint embedding of brain networks.Specifically, we use graph convolutions to learn the structural and functionaljoint embedding, where the graph structure is defined with structuralconnectivity and node features are from the functional connectivity. Moreover,we propose to preserve the community structure of brain networks in the graphconvolutions by considering the intra-community and inter-community propertiesin the learning process. Furthermore, we use Siamese architecture which modelsthe pair-wise similarity learning to guide the learning process. To evaluatethe proposed approach, we conduct extensive experiments on two real brainnetwork datasets. The experimental results demonstrate the superior performanceof the proposed approach in structural and functional joint embedding forneurological disorder analysis, indicating its promising value for clinicalapplications.

Community-preserving Graph Convolutions for Structural and Functional Joint Embedding of Brain Networks